Data-driven synthesis of composite-feature detectors for 3D image analysis

Dosil, Raquel; Pardo, Xosé M.; Fdez-Vidal, Xosé R.

doi:10.1016/j.imavis.2005.11.005

Cited by 13 publications

(3 citation statements)

References 103 publications

(205 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The transfer function (G) of a 3D Log-Gabor filter in the frequency domain (1) is constructed as the product of two components: a one dimensional Log Gabor function that controls the frequencies to which the filter responds and a rotational symmetric angular Gaussian function that controls the orientation selectivity of the filter [11].…”

Section: D Local Phase Symmetry Featurementioning

confidence: 99%

Bone Segmentation and Fracture Detection in Ultrasound Using 3D Local Phase Features

Hacihaliloglu¹,

Abugharbieh²,

Hodgson

et al. 2008

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2008

View full text Add to dashboard Cite

Abstract. 3D ultrasound (US) is increasingly considered as a viable alternative imaging modality in computer-assisted orthopaedic surgery (CAOS) applications. Automatic bone segmentation from US images, however, remains a challenge due to speckle noise and various other artifacts inherent to US. In this paper, we present intensity invariant three dimensional (3D) local image phase features, obtained using 3D Log-Gabor filter banks, for extracting ridge-like features similar to those that occur at soft tissue/bone interfaces. Our contributions include the novel extension of 2D phase symmetry features to 3D and their use in automatic extraction of bone surfaces and fractured fragments in 3D US. We validate our technique using phantom, in vitro, and in vivo experiments. Qualitative and quantitative results demonstrate remarkably clear segmentations results of bone surfaces with a localization accuracy of better than 0.62mm and mean errors in estimating fracture displacements below 0.65mm, which will likely be of strong clinical utility.

show abstract

Section: D Local Phase Symmetry Featurementioning

confidence: 99%

Bone Segmentation and Fracture Detection in Ultrasound Using 3D Local Phase Features

Hacihaliloglu¹,

Abugharbieh²,

Hodgson

et al. 2008

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2008

View full text Add to dashboard Cite

show abstract

“…5 ) × log ( κ β ) . The Log‐Gabor filter is extended to 3D by multiplying the transfer function with a rotational symmetric angular Gaussian function ( A j ) that controls the orientation selectivity of the filter which results in a 3D Log‐Gabor filter , 3DG ij , with a transfer function given as:

\begin{matrix} 3 D G_{italicij} = G_{i} (p | (κ, ω_{oi})) \times A_{j} (p | (ϕ_{j} θ_{j} σ_{α})), \\ 3 D G_{italicij} = \exp (- \frac{lo g^{2} (\frac{ω ((), p)}{ω_{0 i}})}{2 lo g^{2} (κ_{β})}) \times \exp (- \frac{α {((), p, ϕ_{j}, θ_{j})}^{2}}{2 σ_{α}^{2}}) . \end{matrix}

Here the subscripts ‘ i ’ and ‘ j ’ denote the scale and orientation of the 3D filter, respectively. The angle between the direction of the filter, which is specified by the azimuth ( ϕ j ) and elevation ( θ j ) angles, and the position vector of a given point p in the frequency domain is given by α ( p , ϕ j , θ j ) = arccos( p ⋅ ν j /|| p ||), where ν j = (cos ϕ j × cos θ j , cos ϕ j × sin θ j , sin ϕ j ) is a unit vector in the filter's direction.…”

Section: Methodsmentioning

confidence: 99%

“…The spatial bandwidth (β) of the filter is calculated from the ratio of κ β using the following formula: β = -2 × (2/ log 2) (0.5) × log (κ β ) (23,24). The Log-Gabor filter is extended to 3D by multiplying the transfer function with a rotational symmetric angular Gaussian function (A j ) that controls the orientation selectivity of the filter (22,27) which results in a 3D Log-Gabor filter (22,27), 3DG ij , with a transfer function given as:…”

Section: D Local Phase-based Filter Designmentioning

confidence: 99%